АНАЛИЗ И ВЫБОР МЕТОДИКИ В РЕШЕНИИ ЗАДАЧ ИНТЕЛЛЕКТУАЛИЗАЦИИ СИСТЕМ ПРОГНОЗИРОВАНИЯ ТЕРМОФЛУКТУАЦИОННЫХ ПРОЦЕССОВ В КАБЕЛЬНЫХ СЕТЯХ

Abstract

The article is devoted to research on the creation of diagnostics and prediction ofthermofluctuation processes of insulating materials of power cable lines (PCL) of electric powersystems based on such methods of artificial intelligence as neural networks and fuzzy logic. Thenecessity of developing a better methodology for the analysis of thermal conditions in PCL isshown. The urgency of the task of creating neural networks (NS) for assessing the throughput,calculating and predicting the temperature of PCL conductors in real time based on the data ofthe temperature monitoring system, taking into account changes in the current load of the line andthe external conditions of the heat sink, is substantiated. Based on the main criteria, traditionaland neural network algorithms for forecasting are compared, and the advantage of NS methods isshown. The classification of NS methods and models for predicting the temperature conditions ofcosmic rays has been carried out. To solve the problem of forecasting the PCL resource, a networkwas selected with direct data distribution and back propagation of the error, because networks of this type, together with an activation function in the form of a hyperbolic tangent, are tosome extent a universal structure for many problems of approximation, approximation, and forecasting.A neural network has been developed to determine the temperature regime of a currentcarryingcore of a power cable. A comparative analysis of the experimental and calculated characteristicsof the temperature distributions was carried out, while various load modes and thefunctions of changing the cable current were investigated. When analyzing the data, it was determinedthat the maximum deviation of the data received from the neural network from the data ofthe training sample was less than 2.5 %, which is an acceptable result. To increase the accuracy, alarge amount of input and output data was used when training the network, as well as some refinementof its structure. The model allows you to evaluate the current state of isolation and predictthe residual life of PCL. The model can be used in devices and systems for continuous diagnosisof power cables by temperature conditions.